1. Temporal and statistical insights into multivariate time series forecasting of corn outlet moisture in industrial continuous-flow drying systemsMarko Simonič, Simon Klančnik, 2025, izvirni znanstveni članek Opis: Corn drying is a critical post-harvest process to ensure product quality and compliance with moisture standards. Traditional optimization approaches often overlook dynamic interactions between operational parameters and environmental factors in industrial continuous flow drying systems. This study integrates statistical analysis and deep learning to predict outlet moisture content, leveraging a dataset of 3826 observations from an operational dryer. The effects of inlet moisture, target air temperature, and material discharge interval on thermal behavior of the system were evaluated through linear regression and t-test, which provided interpretable insights into process dependencies. Three neural network architectures (LSTM, GRU, and TCN) were benchmarked for multivariate time-series forecasting of outlet corn moisture, with hyperparameters optimized using grid search to ensure fair performance comparison. Results demonstrated GRU’s superior performance in the context of absolute deviations, achieving the lowest mean absolute error (MAE = 0.304%) and competitive mean squared error (MSE = 0.304%), compared to LSTM (MAE = 0.368%, MSE = 0.291%) and TCN (MAE = 0.397%, MSE = 0.315%). While GRU excelled in average prediction accuracy, LSTM’s lower MSE highlighted its robustness against extreme deviations. The hybrid methodology bridges statistical insights for interpretability with deep learning’s dynamic predictive capabilities, offering a scalable framework for real-time process optimization. By combining traditional analytical methods (e.g., regression and t-test) with deep learning-driven forecasting, this work advances intelligent monitoring and control of industrial drying systems, enhancing process stability, ensuring compliance with moisture standards, and indirectly supporting energy efficiency by reducing over drying and enabling more consistent operation.
Ključne besede: advanced drying technologies, continuous flow drying, time-series forecasting, LSTM, GRU, TCN, deep learning, statistical analysis, optimization of the drying process
Objavljeno v DKUM: 03.11.2025; Ogledov: 0; Prenosov: 3
 Celotno besedilo (3,02 MB)
Gradivo ima več datotek! Več... |
2. OpenHENS: an open-source tool for heat exchanger network synthesisKeegan Keysers Hall, Andreja Nemet, Zdravko Kravanja, Timothy Gordon Walmsley, 2026, izvirni znanstveni članek Opis: The synthesis of heat exchanger networks (HENs) is an NP hard problem, made even more difficult by the requirement of commercial software licenses and coding ability. This paper introduces OpenHENS, a first-of-itskind open-source tool for HEN synthesis. In the literature, HEN synthesis based on mathematical programming almost exclusively relies on commercial MINLP (mixed-integer non-linear programming) solvers (e.g., BARON, Gurobi, etc.). Open source MINLP solvers, in contrast, lack the robustness, scalability and quality that are the hallmarks of commercial solvers. To overcome this challenge, OpenHENS embeds a novel three-step synthesis method that gradually increases the complexity of the model. The first two steps identify economically viable and thermodynamically feasible heat exchanger matches, removing the non-viable matches and reducing the problem size. In the third step, numerous HEN designs are obtained by evolving promising networks to obtain families of near-optimal solutions. OpenHENS was tested on thirteen benchmark problems and seven of the solutions were within 2 % of the total annualised cost (TAC) best-known solutions from literature. In eleven of the benchmark problems, OpenHENS returned more than 10 unique networks within 2 % of the best solution, enabling the engineer to select the most practical design with minimal cost difference. OpenHENS demonstrates that open-source software, when developed correctly, offers comparable performance to commercial software while promoting greater accessibility in industry.
Ključne besede: heat exchanger network, process integration, optimization, mathematical programming, open source, Phyton
Objavljeno v DKUM: 03.11.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (17,21 MB) |
3. Engineering Materials and Process Technologies : 2nd Conference of Programme Groups of the Faculty of Mechanical Engineering University of Maribor, Book of Abstracts2025 Opis: The publication presents an overview of the research achievements of Programm Groups of the Faculty of Mechanical Engineering: P2-0424 Design of Novel Properties of (Nano)Materials & Applications, P2-0063 Design of Cellular Structures, P2-0120 Technologies of Metastable Materials, P2-0118 Textile Chemistry and Advanced Textile Materials, and P2-0196 Research in Power, Process, and Environmental Engineering from 2024 to 2025. Members of the program group present their research innovations and progress achieved within the framework of the program group's activities.
Ključne besede: advanced textile materials, composites, nanomaterials, biotechnology, surface functionalization and modification, cellular structures, metastable materials, power, process and environmental engineering
Objavljeno v DKUM: 03.11.2025; Ogledov: 0; Prenosov: 2
Celotno besedilo (7,24 MB)
Gradivo ima več datotek! Več... |
4. Students’ perceptions of peer feedback in lower elementary school gradesMarija Sablić, Ana Mirosavljević, Ana Maria Marinac, 2025, izvirni znanstveni članek Opis: This paper presents the results of a study conducted on seventeen first- to fourthgrade elementary school students, the aim of which was to examine the students’ perceptions and assessments of the importance of peer feedback and the ways in which peer feedback is carried out. This paper emphasizes the need to raise awareness of the basic skills that are necessary for effective peer feedback – the development of critical thinking, evaluation, observation skills, communication skills, the development of empathy, self-confidence, and the development of respect for others.
Ključne besede: learning process, peer feedback, school, student, teaching
Objavljeno v DKUM: 02.10.2025; Ogledov: 0; Prenosov: 6
Celotno besedilo (824,38 KB)
Gradivo ima več datotek! Več... |
5. Investigation of the influencing parameters of the ▫$H_2O_2-assisted$▫ photochemical treatment of waste liquid from the hydrothermal carbonization process in a microreactor flow systemAleksandra Petrovič, Tjaša Cenčič, Silvo Hribernik, Andreja Nemet, 2025, izvirni znanstveni članek Opis: Due to its complex composition and toxicity, the waste liquid from hydrothermal carbonization (HTC) poses a serious environmental challenge that must be addressed before disposal. In this study, the photochemical treatment of HTC liquid in a microreactor flow system was investigated. The effects of wavelength, the presence of atmospheric oxygen, oxidizing agent (H2O2) and catalyst (FeSO4), residence time and pH on the efficiency of the photo-treatment were investigated. In addition, the influence of the addition of deep eutectic solvent (DES) on photo-treatment was studied. The results showed that the photochemical treatment was more efficient at 365 nm than at 420 nm, and that the acidic conditions gave better results than the basic ones. UV365 treatment in the presence of H2O2 (at a dosage of 1 vol%) resulted in removal efficiencies of 31.6% for COD, 17.6% for TOC, 16.9% for NH4-N and 17.2% for PO4-P. The addition of FeSO4 caused coagulation/flocculation effects, but improved phosphorus removal. The addition of DES resulted in slight discolouration of the liquid and proved unsuccessful in COD removal. The GC-MS analysis and 3D-EEM spectra showed significant changes in the fate of organics and in the fluorescence intensity of aromatic proteins and humic acid-like substances. Photochemical treatment in a microreactor flow system in the presence of H2O2 under the selected operating conditions reduced the content of organics and nutrients in the HTC liquid, but the process liquids still showed toxic effects on the organisms V. fischeri and Daphnia magna.
Ključne besede: hydrothermal treatment, waste process liquid, photochemical treatment, hydrogen peroxide, microreactor flow system
Objavljeno v DKUM: 25.09.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (2,64 MB) |
6. Slovenia’s nuclear energy pathway : strategic expansion, regulatory hurdles, and future prospectsNataša Samec Berghaus, Aleš Ferčič, Klemen Drnovšek, 2025, izvirni znanstveni članek Opis: Slovenia boasts a longstanding tradition in the field of nuclear energy generation, with the Krško Nuclear Power Plant (NEK) traditionally playing an important role in the national energy system. As the country plans its future energy mix, nuclear power continues to figure prominently, not least in light of the proposed JEK2 project. However, the development of new nuclear facilities faces significant challenges, including lengthy regulatory procedures, complex construction processes, financial uncertainties, long-term issues related to nuclear fuel supply and waste management, as well as broader concerns regarding public acceptance. This article focuses on the legal dimensions shaping Slovenia’s nuclear energy pathway, with non-legal considerations introduced solely insofar as they serve to elucidate or reinforce the legal analysis. Within this framework, the licensing process in Slovenia is examined in detail, with particular regard to its multi-step structure and the administrative challenges it poses. In addition, issues related to public procurement procedures, transparency, and governance are well discussed, particularly considering past infrastructure project failures. While Small Modular Reactors (SMRs) are being explored as a potential long-term solution, their licensing and deployment remain uncertain due to regulatory and spatial constraints. The paper also emphasises the importance of strategic workforce planning. Ultimately, the attainment of a resilient and secure energy future in Slovenia demands not only continued investment in nuclear infrastructure, but also a broader consideration of energy efficiency, security risks, and long-term sustainability—considerations which are addressed herein.
Ključne besede: nuclear energy, Krško NPP, JEK2, nuclear licensing, environmental consent, permitting process, Nuclear Safety Administration, energy security, nuclear laws, Slovenia
Objavljeno v DKUM: 28.08.2025; Ogledov: 0; Prenosov: 6
Celotno besedilo (422,15 KB)
Gradivo ima več datotek! Več... |
7. Integrating simulation modelling for sustainable, human-centred Industry 5.0: ESG-based evaluation in collaborative workplacesRobert Ojsteršek, Aljaž Javernik, Borut Buchmeister, 2024, izvirni znanstveni članek Opis: This research explores the role of simulation modelling in the development of human-centred, sustainable manufacturing processes in the context of Industry 5.0. We analyse collaborative workplaces where humans and collaborative robots (CR) work together, emphasizing the environmental, social, and governance (ESG) criteria. The research work focuses on how personalized CR parameters and optimized work environments contribute to improved productivity, well-being, and sustainability. Through simulations, the paper evaluates the operational efficiency of both manual assembly and human-robot collaborative (HRC) setups, providing insight into the economic, environmental, and social impacts of Industry 5.0 manufacturing systems. The results show significant improvements in sustainability, productivity, and worker well-being achieved through adaptive CR integration and ESG-driven engineering practices.
Ključne besede: human-centred manufacturing, simulation modelling, sustainability – ESG, industry 5.0, collaborative workplace, human-robot interaction, assembly process
Objavljeno v DKUM: 28.08.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (1,09 MB)
Gradivo ima več datotek! Več... |
8. Digital transformation and business model innovation: enhancing productivity in the Croatian maritime transport sectorMarija Jović Mihanović, Saša Aksentijević, Edvard Tijan, Gregor Lenart, 2025, izvirni znanstveni članek Opis: This research investigates how business model changes induced by digital transformation impact productivity within the maritime transport sector in Croatia. Given the
limited existing literature addressing digital transformation’s productivity implications,
specifically in maritime contexts, this study aims to identify and analyze key mediating factors. An online survey conducted among Croatian maritime transport stakeholders resulted in 82 valid responses, which were statistically analyzed using descriptive
statistics, Spearman’s correlation, and principal component analysis (PCA). The study
identifies two primary dimensions of business model changes—innovation and process
digitalization—that significantly correlate with increased productivity. Key influencing
factors include the digitalization of internal and external business processes, development
of new digital revenue streams, introduction of innovative services, and novel pricing
models. Results underscore the importance of targeted digital transformation initiatives
and serve as a valuable reference for maritime transport stakeholders, aiming to enhance
their productivity and competitiveness through digital innovation.
Ključne besede: digital transformation, maritime transport, productivity, business model innovation, process digitalization, Croatia, principal component analysis
Objavljeno v DKUM: 26.08.2025; Ogledov: 0; Prenosov: 4
Celotno besedilo (430,91 KB)
Gradivo ima več datotek! Več... |
9. Leveraging ChatGPT for enhanced logical analysis in the theory of constraints thinking processTomaž Aljaž, 2024, izvirni znanstveni članek Opis: Background/Purpose: Artificial intelligence (AI) has traditionally been used for quantitative analysis using explicit data. However, much of the information critical to decision making remains undocumented and is not stored in a structured way. This study explores the integration of AI, specifically ChatGPT, into Theory of Constraints (TOC) Thinking Process (TP) tools. Method: In this study, we applied ChatGPT to a real-world IT project management case using a variety of research methods, including international literature analysis, observation, and personal experience. The use of the TOC TP allowed us to understand the decision-making process of ChatGPT and to systematically explore its advantages and limitations in creating logical trees of TOC TP. Results: ChatGPT significantly enhanced efficiency and depth in TOC TP data collection and analysis, effectively addressing logical leaps for more coherent structures. It also promoted deeper analytical thinking and aided root cause identification. The integration of ChatGPT into the TOC TP process led to faster decision-making, reduced bias, and clearer analysis. Challenges of ChatGPT including the need for human oversight, specific TOC TP training, and ethical considerations were noted. Conclusion: This study provides an initial investigation into the use of ChatGPT in TOC TP tools. The results suggest that ChatGPT has the potential to be a valuable tool for organizations seeking to improve their decision making and performance. However, further research is needed to validate these findings and explore the full potential of AI in TOC TP.
Ključne besede: ChatGPT, artificial intelligence, Theory of Constraints, theory of constraints thinking process, logical analysis, decision making, structured analysis framework
Objavljeno v DKUM: 13.08.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (2,21 MB)
Gradivo ima več datotek! Več... |
10. An analysis of methods and techniques used for business process improvementEva Krhač Andrašec, Benjamin Urh, Matjaž Roblek, Tomaž Kern, 2024, izvirni znanstveni članek Opis: Background: More than 50 process-based approaches, methods, and techniques have been developed in recent decades to achieve more efficient operation of organizational systems. Due to increasingly rapid changes in the business environment, the question of which method or technique will have the most significant impact on increasing the organizational system’s competitive advantage is becoming increasingly important. Purpose: In the presented research, we focused on identifying methods and techniques often cited in the literature and most often used in practice as efficient for improving business processes. Methods: We prepared a 4-phase structured review of the available literature and supported the findings with survey research. Results and Conclusion: Based on the results, we designed a set of appropriate, most frequently used, and efficient methods and techniques for improving business processes. The completed research can serve as a starting point for answering the question about the appropriate methods and techniques for the chosen approach. In continuing the research, it would be reasonable to check other properties and the use of methods and techniques.
Ključne besede: business process management, business process improvement, approaches, methods, techniques
Objavljeno v DKUM: 13.08.2025; Ogledov: 0; Prenosov: 4
Celotno besedilo (755,78 KB)
Gradivo ima več datotek! Več... |
